Recent Articles

Large language models (LLMs) have demonstrated significant potential in academic research but face challenges in generating accurate citations. The issue of hallucinated references—well-formatted but fictitious citations—arises due to LLMs' limited access to subscription-based databases and their reliance on probabilistic text generation. This letter discusses two key approaches to mitigating these issues. First, retrieval-augmented generation (RAG) combined with Hallucination Aware Tuning (HAT) improves citation integrity by integrating external databases and employing hallucination detection models. However, even RAG-HAT systems may still misinterpret source content. Second, we propose the development of “Reference-Accurate” Academic LLMs by major global publishers, which would be trained exclusively on rigorously verified academic literature, ensuring that all citations generated are authentic and traceable. We recommend a dual approach integrating RAG-HAT with publisher-backed academic LLMs, along with human oversight, to enhance AI-assisted scholarly communication. Future research should evaluate the accuracy and reliability of these methods to promote responsible AI use in academia.

The use of extended reality (XR) technologies in health care can potentially address some of the significant resource and time constraints related to delivering training for health care professionals. While substantial progress in realizing this potential has been made across several domains, including surgery, anatomy, and rehabilitation, the implementation of XR in mental health training, where nuanced humanistic interactions are central, has lagged.


English for Medical Purposes (EMP) is essential for medical students as it serves as a foundational language for medical communication and education. However, students often undervalue its importance within the medical curriculum. Given their demanding schedules and workload, educational methods for EMP must align with their needs. Structured online learning offers flexibility and convenience, yet limited research has explored its exclusive application for EMP in undergraduate medical education.


The Generative Pre-trained Transformer (GPT-4) is a large language model (LLM) trained and fine-tuned on an extensive dataset. After the public release of its predecessor in November 2022, the use of LLMs has seen a significant spike in interest, and a multitude of potential use cases have been proposed. In parallel, however, important limitations have been outlined. Particularly, current LLM encounters limitations, especially in symbolic representation and accessing contemporary data. The recent version of GPT-4, alongside newly released plugin features, has been introduced to mitigate some of these limitations.

Project ECHO is an innovative program that uses videoconferencing technology to connect healthcare providers with experts. The model has been successful in reaching healthcare providers in rural and underserved areas and positively impacting clinical practice. ECHO Idaho, a replication partner, has developed programming that has increased knowledge and confidence of healthcare professionals throughout the state of Idaho. Although the ECHO model has a demonstrated ability to recruit, educate, and train healthcare providers, barriers to attending Project ECHO continuing education (CE) programs remain. The asynchronous nature of podcasts could be used as an innovative medium to help address barriers to CE access that healthcare professionals face. The ECHO Idaho “Something for the Pain” podcast was developed to increase CE accessibility to rural and frontier providers, while upscaling their knowledge of and competence to treat and assess substance use disorders, pain, and behavioral health conditions.


Healthcare practitioners use Clinical Decision Support Systems (CDSS) as an aid in the crucial task of clinical reasoning and decision making. Traditional CDSS are Online Repositories (OR) and Clinical Practice Guidelines (CPG). Recently, Large Language Models (LLMs) like ChatGPT have emerged as potential alternatives. They have proven to be powerful innovative tools, yet they are not devoid of worrisome risks.
Preprints Open for Peer-Review
Open Peer Review Period:
-
Open Peer Review Period:
-
Open Peer Review Period:
-